Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback

• URL: http://arxiv.org/abs/2410.05434v1
• Date: Mon, 7 Oct 2024 18:55:53 GMT
• Title: Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback
• Authors: Sanjiban Choudhury, Paloma Sodhi,
• Abstract summary: Large language models (LLMs) show impressive decision-making abilities. Current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers.
• Score: 12.61197377492141
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually improves LLM agents using feedback from AI expert teachers. Our key insight is to equip the expert teachers with a privileged state -- information that is available during training but hidden at test time. This allows even weak experts to provide precise guidance, significantly improving the student agent's performance without access to privileged information at test time. We evaluate LEAP on diverse decision-making benchmarks, including text-based games (ALFWorld), web navigation (WebShop), and interactive coding (Intercode Bash). Our experiments show that LEAP (1) outperforms behavior cloning and ReAct baselines (2) enables weak student models (e.g., Llama3-8B) to exceed the performance of strong teacher models (GPT4-o), and (3) allows weak models to self-improve using privileged versions of themselves. We also provide a theoretical analysis showing that LEAP's success hinges on balancing privileged information with the student's realizability, which we empirically validate. Our code is available at https://leap-llm.github.io

Related papers

• Expanding the Capabilities of Reinforcement Learning via Text Feedback [49.561885700139676]
  We formalize a multi-turn RL setup, RL from Text Feedback (RLTF), where text feedback is available during training but not at inference.<n>To do this, we propose two methods: Self Distillation (RLTF-SD), which trains the single-turn policy to match its own feedback-conditioned second-turn generations; and Feedback Modeling (RLTF-FM), which predicts the feedback as an auxiliary objective.<n>Our results show that both methods consistently outperform strong baselines across benchmarks.
  arXiv  Detail & Related papers  (2026-02-02T18:56:56Z)
• SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data [65.56911325914582]
  We propose Self-play Reinforcement Learning (SeRL) to bootstrap Large Language Models (LLMs) training with limited initial data.<n>The proposed SeRL yields results superior to its counterparts and achieves performance on par with those obtained by high-quality data with verifiable rewards.
  arXiv  Detail & Related papers  (2025-05-25T13:28:04Z)
• Is your multimodal large language model a good science tutor? [14.505855717011725]
  Multimodal large language models (MLLMs) demonstrate impressive performance on scientific reasoning tasks.<n>We propose a framework that evaluates MLLMs as science tutors using a comprehensive educational rubric and a simulated student model.
  arXiv  Detail & Related papers  (2025-05-09T20:38:23Z)
• AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories [59.214178488091584]
  We propose AgentRewardBench, the first benchmark to assess the effectiveness of LLM judges for evaluating web agents. Using our benchmark, we evaluate 12 LLM judges and find that no single LLM excels across all benchmarks. We also find that the rule-based evaluation used by common benchmarks tends to underreport the success rate of web agents.
  arXiv  Detail & Related papers  (2025-04-11T19:49:22Z)
• Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Study [0.0]
  Large Language Models (LLMs) hold promise as dynamic instructional aids. Yet, it remains unclear whether LLMs can replicate the adaptivity of intelligent tutoring systems (ITS)
  arXiv  Detail & Related papers  (2025-04-07T23:57:32Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods [1.9799527196428242]
  Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes. LMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on unlearning benchmarks.
  arXiv  Detail & Related papers  (2024-11-18T22:31:17Z)
• Learning to Ask: When LLMs Meet Unclear Instruction [49.256630152684764]
  Large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. We evaluate the performance of LLMs tool-use under imperfect instructions, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions.
  arXiv  Detail & Related papers  (2024-08-31T23:06:12Z)
• LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
  "LLMs-as-Instructors" framework autonomously enhances the training of smaller target models. Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model. Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
  arXiv  Detail & Related papers  (2024-06-29T17:16:04Z)
• AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models [95.09157454599605]
  Large Language Models (LLMs) are becoming increasingly powerful, but they still exhibit significant but subtle weaknesses. Traditional benchmarking approaches cannot thoroughly pinpoint specific model deficiencies. We introduce a unified framework, AutoDetect, to automatically expose weaknesses in LLMs across various tasks.
  arXiv  Detail & Related papers  (2024-06-24T15:16:45Z)
• Re-ReST: Reflection-Reinforced Self-Training for Language Agents [101.22559705696885]
  Self-training in language agents can generate supervision from the agent itself. We present Reflection-Reinforced Self-Training (Re-ReST), which uses a textitreflector to refine low-quality generated samples.
  arXiv  Detail & Related papers  (2024-06-03T16:21:38Z)
• Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models [21.052532074815765]
  We introduce the Lafite-RL (Language agent feedback interactive Reinforcement Learning) framework. It enables RL agents to learn robotic tasks efficiently by taking advantage of Large Language Models' timely feedback. It outperforms the baseline in terms of both learning efficiency and success rate.
  arXiv  Detail & Related papers  (2023-11-04T11:21:38Z)
• How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging [28.321080454393687]
  Large Language Models (LLMs) now excel at generative skills and can create content at impeccable speeds. Human novices play the role of Teaching Assistants and help LLM-powered teachable agents code. We introduce Hypo, a novel system to facilitate deliberate practice on debug, where human novices play the role of Teaching Assistants and help LLM-powered teachable agents code.
  arXiv  Detail & Related papers  (2023-10-08T21:39:47Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)
• Self-Checker: Plug-and-Play Modules for Fact-Checking with Large Language Models [75.75038268227554]
  Self-Checker is a framework comprising a set of plug-and-play modules that facilitate fact-checking. This framework provides a fast and efficient way to construct fact-checking systems in low-resource environments.
  arXiv  Detail & Related papers  (2023-05-24T01:46:07Z)
• Language Model Self-improvement by Reinforcement Learning Contemplation [13.152789365858812]
  This paper introduces a novel unsupervised method called LanguageModel Self-Improvement by Reinforcement Learning Contemplation (SIRLC) As a student, the model generates answers to unlabeled questions, while as a teacher, it evaluates the generated text and assigns scores accordingly. We demonstrate that SIRLC can be applied to various NLP tasks, such as reasoning problems, text generation, and machine translation.
  arXiv  Detail & Related papers  (2023-05-23T19:25:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.